HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
Compress tool outputs, logs, files, RAG chunks before LLM for 60-95% less tokens
github.com/chopratejas
discuss
2 days ago
gmays
4 points
2.
▲
A Compression Tool for LLM Reads. Est. 60-95% Fewer Tokens
github.com/chopratejas
discuss
a month ago
botacode
4 points
3.
▲
Show HN: Headroom (OSS): Cuts LLM costs by 85%
github.com/chopratejas
5 comments
5 months ago
chopratejas
3 points
4.
▲
Headroom – LLM Input Compression
github.com/chopratejas
discuss
22 days ago
lgats
3 points
5.
▲
Headroom – context optimization layer for tool-using agents
github.com/chopratejas
2 comments
5 months ago
chopratejas
2 points
6.
▲
TokenMinMaxing
github.com/chopratejas
discuss
4 days ago
droppedasbaby
2 points
7.
▲
Headroom
github.com/chopratejas
discuss
5 days ago
marc__1
2 points
8.
▲
Show HN: Headroom – Reversible context compression for LLMs(~60% cost reduction)
github.com/chopratejas
1 comment
5 months ago
chopratejas
1 points
9.
▲
The Context Optimization Layer for LLM Applications
github.com/chopratejas
discuss
4 months ago
selvan
1 points